CN107315884B - Building energy consumption modeling method based on linear regression - Google Patents
Building energy consumption modeling method based on linear regression Download PDFInfo
- Publication number
- CN107315884B CN107315884B CN201710537577.XA CN201710537577A CN107315884B CN 107315884 B CN107315884 B CN 107315884B CN 201710537577 A CN201710537577 A CN 201710537577A CN 107315884 B CN107315884 B CN 107315884B
- Authority
- CN
- China
- Prior art keywords
- energy consumption
- historical data
- data
- building
- fitting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012417 linear regression Methods 0.000 title claims abstract description 22
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims description 38
- 230000001419 dependent effect Effects 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 17
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000011425 standardization method Methods 0.000 claims 1
- 238000004134 energy conservation Methods 0.000 abstract description 4
- 230000009467 reduction Effects 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 27
- 238000011160 research Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000002759 z-score normalization Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Quality & Reliability (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a building energy consumption modeling method based on linear regression, which comprises the following steps: acquiring historical data of all energy consumption units in a building; preprocessing all historical data; applying linear regression analysis to the classified data to fit and construct a regression model; and predicting the future expected energy consumption value of the energy consumption component and the future expected total energy consumption value of the building according to the objective function. The building energy consumption modeling method can effectively predict the consumption condition of building energy, and achieves the purposes of energy conservation and consumption reduction by controlling the influence conditions.
Description
Technical Field
The invention relates to the technical field of building energy consumption, in particular to a building energy consumption modeling method based on linear regression.
Background
The building energy consumption analysis is the basis for determining a reasonable energy-saving strategy, is one of research hotspots of energy-saving and consumption-reducing work, and a plurality of scholars at home and abroad deeply research the building energy consumption analysis and modeling method. These studies fall into two categories: the first type mainly takes a building structure as a research object, building energy consumption time-by-time simulation software is adopted to predict energy consumption in a building design stage, and the prediction is greatly different from the actual situation due to the uncertainty of a using mode of a person for a building; the second type is mainly to collect all information of the building in the operation stage on the basis of the existing building, and to study the energy consumption data to know the generation rule of the energy consumption.
In the prior art, the building energy consumption research method has an insufficient detailed description on the energy consumption rule, and cannot accurately predict the building energy consumption.
Disclosure of Invention
The invention provides a building energy consumption modeling method based on linear regression, which solves or partially solves the technical problems that the building energy consumption research method in the prior art is not careful in describing energy consumption rules and cannot accurately predict building energy consumption, realizes effective prediction of the consumption condition of building energy, and achieves the technical effects of saving energy and reducing consumption by controlling influence conditions.
The building energy consumption modeling method based on linear regression provided by the invention comprises the following steps:
obtaining historical data of all energy consumption units in the building; the historical data includes: the energy consumption value of each energy consumption unit is endowed with marking information, and the total energy consumption value of the building; the marking information includes: time, outdoor temperature, application scenario, service; the time includes: each time period is recorded by year, month, day, hour or minute;
preprocessing all the historical data; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all the historical data; all the historical data meet normal distribution after being subjected to normalization processing; the classification processing comprises the following steps: performing data classification on the historical data according to the four dimensions of the time, the outdoor temperature, the application scene and the business to obtain four subclasses, subdividing the four subclasses by using a decision tree model to obtain classified data, and finally constructing a training data set by using all the classified data;
applying linear regression analysis to the classified data to fit and construct a regression model; the linear regression analysis fitting comprises: taking each time period in the time as an independent variable, and taking the energy consumption value corresponding to the time period as a dependent variable, and performing linear fitting to obtain a first fitting relational expression; taking the square of the outdoor temperature as an independent variable and the energy consumption value corresponding to the outdoor temperature as a dependent variable, and performing linear fitting to obtain a second fitting relational expression; taking the application scene as an independent variable and the energy consumption value corresponding to the application scene as a dependent variable, and performing linear fitting to obtain a third fitting relational expression; taking the service as an independent variable and the energy consumption value corresponding to the service as a dependent variable, and performing linear fitting to obtain a fourth fitting relational expression; constructing a target function according to the first fitting relation, the second fitting relation, the third fitting relation and the fourth fitting relation; the objective function is the regression model; the objective function takes the time, the outdoor temperature, the application scene and the service as independent variables, and takes the energy consumption value of the energy consumption unit as a dependent variable;
and predicting the future expected energy consumption value of the energy consumption unit and the future expected total energy consumption value of the building according to the objective function.
Preferably, the building energy consumption modeling method further includes:
measuring to obtain real-time data endowed with marking information;
drawing a scatter plot comparison graph according to the real-time energy consumption value of the energy consumption unit in the real-time data and the expected energy consumption value;
and when the scatter plot approaches to a straight line represented by x, determining that the objective function is a reasonable function, otherwise, the objective function is unreasonable and needs to be reconstructed.
Preferably, the marking information of the real-time data includes: time, outdoor temperature, application scenario, service.
Preferably, the building energy consumption modeling method further includes:
solving an extreme value of the energy consumption unit and a total energy consumption extreme value of the building by applying a Lagrange multiplier method to the target function;
the Lagrange multiplier method specifically comprises the following steps: and controlling the rest of independent variables by limiting one or more independent variables in the time, the outdoor temperature, the application scene and the business, so as to obtain an energy consumption extreme value of the energy consumption unit and a total energy consumption extreme value of the building, and further determine the independent variable which has the greatest influence on energy consumption.
Preferably, the normalization process uses a Z-score normalization method using a transformation function
Processing the historical data to enable the processed historical data to meet normal distribution;
wherein μ is a mean of all the historical data, σ is a standard deviation of all the historical data, x is one of the historical data, and x*For the history data after the x processing。
Preferably, after the normalization processing and before the classification processing, vectorization processing is performed on the historical data;
the vectorization processing specifically includes: and sorting the historical data and storing the sorted historical data into a matrix according to a set rule so as to carry out the classification treatment.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
due to the adoption of the method, historical data of all energy consumption units in the building are obtained, and all the historical data are preprocessed to obtain classified data; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all historical data; the classification data is fitted and constructed into a target function by linear regression analysis, so that a regression model meeting historical data is obtained, the rule of energy consumption is mined, and the future building energy consumption is accurately predicted; therefore, the technical problems that the building energy consumption research method in the prior art is not careful in description of the energy consumption rule and cannot accurately predict the building energy consumption are effectively solved, the consumption condition of the building energy is effectively predicted, and the purposes of energy conservation and consumption reduction are achieved by controlling the influence condition.
Drawings
Fig. 1 is a schematic flow chart of a building energy consumption modeling method based on linear regression provided by the invention.
Detailed Description
The embodiment of the application provides a building energy consumption modeling method based on linear regression, and solves or partially solves the technical problems that in the prior art, a building energy consumption research method has a less detailed description on an energy consumption rule and cannot accurately predict building energy consumption, and classification data are obtained by preprocessing all historical data of all energy consumption units in a building; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all historical data; and (3) applying linear regression analysis to the classified data to fit and construct a target function, thereby obtaining a regression model meeting historical data, finding out the rule of energy consumption, accurately predicting the future building energy consumption, effectively predicting the consumption condition of building energy, and achieving the technical effects of saving energy and reducing consumption by controlling the influence conditions.
Referring to the attached drawing 1, the building energy consumption modeling method based on linear regression provided by the invention comprises the following steps:
s1: acquiring historical data of all energy consumption units in a building; the historical data includes: the energy consumption value of each energy consumption unit is endowed with marking information and the total energy consumption value of the building; the marking information includes: time, outdoor temperature, application scenario, service; the time includes: the time intervals are each in the form of a time period of years, months, days, hours or minutes.
S2: preprocessing all historical data; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all historical data; all historical data meet normal distribution after normalization processing; the classification treatment comprises the following steps: the historical data is subjected to data classification according to four dimensions of time, outdoor temperature, application scenes and services to obtain four subclasses, the four subclasses are subdivided by using a decision tree model to obtain classified data, and finally, all the classified data are constructed into a training data set.
S3: applying linear regression analysis to the classified data to fit and construct a regression model; linear regression analysis fitting includes: taking each time period in the time as an independent variable and taking the energy consumption value corresponding to the time period as a dependent variable, and performing linear fitting to obtain a first fitting relational expression; taking the square of the outdoor temperature as an independent variable and the energy consumption value corresponding to the outdoor temperature as a dependent variable, and performing linear fitting to obtain a second fitting relational expression; taking the application scene as an independent variable and taking the energy consumption value corresponding to the application scene as a dependent variable, and performing linear fitting to obtain a third fitting relational expression; taking the service as an independent variable and taking the energy consumption value corresponding to the service as a dependent variable, and performing linear fitting to obtain a fourth fitting relational expression; constructing a target function according to the first fitting relation, the second fitting relation, the third fitting relation and the fourth fitting relation; the target function is a regression model; the objective function takes time, outdoor temperature, application scene and service as independent variables, and takes the energy consumption value of the energy consumption unit as a dependent variable.
S4: and predicting the future expected energy consumption value of the energy consumption unit and the future expected total energy consumption value of the building according to the objective function.
The modeling method comprises the following basic ideas: acquiring historical data and real-time data; classifying the acquired data; classifying the data and the influence factors; the influence factors are analyzed, linear fitting is carried out on the analyzed curve, the influence factors are fed back through the curve and the prediction result, a closed loop is formed, and finally the accuracy of the analysis result and the optimality of the whole process are achieved; and analyzing the energy consumption control conditions by using a Lagrange multiplier method and accurately giving a prediction result according to the analysis result. The modeling method can effectively predict the consumption condition of building energy, and achieves the purposes of energy conservation and consumption reduction by controlling the influence conditions.
Further, the building energy consumption modeling method further comprises the following steps: measuring to obtain real-time data endowed with marking information; drawing a scatter plot comparison graph according to the real-time energy consumption value and the expected energy consumption value of the energy consumption unit in the real-time data; when the scatter plot approaches to a straight line represented by x, the objective function is determined to be a reasonable function, otherwise, the objective function is unreasonable and needs to be reconstructed. The marking information of the real-time data includes: time, outdoor temperature, application scenario, service.
Further, the building energy consumption modeling method further comprises the following steps: solving an extreme value of an energy consumption unit and a total energy consumption extreme value of a building by applying a Lagrange multiplier method to the target function; the Lagrange multiplier method is specifically as follows: and controlling the rest independent variables by limiting one or more independent variables in time, outdoor temperature, application scene and business, further obtaining an energy consumption extreme value of an energy consumption unit and a total energy consumption extreme value of a building, and further determining the independent variable which has the largest influence on energy consumption.
Further, the normalization process adopts a Z-score normalization method and uses a transformation function
Processing the historical data to enable the processed historical data to meet normal distribution; where μ is the mean of all historical data and σ is all historical numbersAccording to the standard deviation, x is one of the historical data, x*Historical data after x processing.
Further, after normalization processing and before classification processing, vectorization processing is carried out on the historical data; the vectorization process specifically comprises: and sorting the historical data and storing the sorted historical data into a matrix according to a set rule so as to carry out classification processing.
The building energy consumption modeling method based on linear regression provided by the application is described in detail by specific embodiments as follows:
step S1: acquiring historical data, including: year, month, day, hour, minute, weather, outdoor temperature, total energy consumption.
Step S2: categorizing historical data and influencing factors, including:
s201: data normalization by transformation function
And processing the historical building energy consumption data to enable the historical building energy consumption data to meet normal distribution, wherein mu is the mean value of all sample data, and sigma is the standard deviation of all sample data.
S202: and vectorizing the data, namely vectorizing the historical data after the normalization processing, storing the data into a matrix according to a certain rule after the data are sorted, and facilitating subsequent analysis and calculation.
S203: data classification, decision tree learning, is the representation of an object with a loss function, which is usually a regularized maximum likelihood function, whose strategy is to minimize the loss function and then use information gain to stabilize the availability of the data. By calculating the entropy value, it can be shown that the larger the entropy, the less usable the data. In the method, historical data are subjected to data classification according to four dimensions of time, outdoor temperature, application scenes and business to obtain four subclasses, the four subclasses are subdivided by using a decision tree model to obtain classified data, finally, a training data set constructed by all the classified data is used for calculating the information entropy of the classified data, and it is assumed that c types of data are mixed in a sample data set D. When constructing a decision tree, according to the dataAnd selecting a certain characteristic value as a node of the tree from the certain sample data set. Is composed of
D represents the classified training data set, c represents the number of data categories, and Pi represents the sample data proportion of category i. In this way, the acquired data is subjected to corresponding data classification and data preprocessing.
Step S3: fitting analysis comprising:
s301: independent variables affect significance analysis, and the relationship of independent variables to dependent variables is analyzed. The analysis of significance of independent variable influence specifically comprises: and judging whether the original hypothesis of the data is obviously different from the data of the plurality of groups through an invalid hypothesis theory obtained through a theory of a small probability event practical impossibility principle, if so, considering the hypothesis to have significance, and receiving or negating the expected hypothesis through the significance. Analyzing the relationship between the independent variable and the dependent variable specifically comprises: through the classification processing in step S203, arguments that need to participate in the calculation are obtained, and the data is processed using the R language in the present embodiment. Firstly, obtaining a scatter diagram of energy consumption values of each variable and a dependent variable from data plot, and preliminarily judging that each of year, month, day, hour, minute and weather is in a linear relation with energy consumption, and the square of outdoor temperature is in a linear relation with energy consumption.
S302: and linear regression fitting analysis, namely establishing a primary model for each variable and dependent variable through an lm function, and inspecting a regression result by using a summary function.
S303: the model was examined and outliers were screened out using residual analysis, here mostly using a residual plot of normalized residual squares and fitted values. The variance is then examined using the gqtest and bptest functions, and if the variance exists, the variance needs to be corrected. Multiple collinearity then needs to be checked, and the model is regressed stepwise using the step function, and is optimal when the AIC value is minimal.
S304: and outputting the model.
Step S4: and analyzing the energy consumption control conditions and predicting future energy consumption data.
The analysis energy consumption control conditions are specifically as follows: and obtaining an energy consumption extreme value by adopting a Lagrange multiplier method, generating a prediction data set under the model through an established regression model, observing whether the predicted value is close to a straight line of which y is equal to x through a scatter plot of the predicted value and the actual value, and if the predicted value is close to the straight line, enabling the prediction model to be available. After the model is obtained, the independent variable is controlled through a Lagrange multiplier method, the extreme value of energy consumption data is obtained, and the independent variable influencing the maximum energy consumption is analyzed. The predicted future energy consumption data is specifically as follows: and predicting the future expected energy consumption value of the energy consumption unit and the future expected total energy consumption value of the building according to the objective function.
The building energy consumption modeling method is generally suitable for energy consumption analysis data preprocessing, is a general data preprocessing method, can effectively predict the consumption condition of building energy, and achieves the purposes of saving energy and reducing consumption by controlling the influence condition.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
due to the adoption of the method, historical data of all energy consumption units in the building are obtained, and all the historical data are preprocessed to obtain classified data; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all historical data; the classification data is fitted and constructed into a target function by linear regression analysis, so that a regression model meeting historical data is obtained, the rule of energy consumption is mined, and the future building energy consumption is accurately predicted; therefore, the technical problems that the building energy consumption research method in the prior art is not careful in description of the energy consumption rule and cannot accurately predict the building energy consumption are effectively solved, the consumption condition of the building energy is effectively predicted, and the purposes of energy conservation and consumption reduction are achieved by controlling the influence condition.
The above-mentioned embodiments, objects, technical solutions and advantages of the present invention are further described in detail, it should be understood that the above-mentioned embodiments are only illustrative of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. A building energy consumption modeling method based on linear regression is characterized by comprising the following steps:
obtaining historical data of all energy consumption units in the building; the historical data includes: the energy consumption value of each energy consumption unit is endowed with marking information, and the total energy consumption value of the building; the marking information includes: time, outdoor temperature, application scenario, service; the time includes: each time period is recorded by year, month, day, hour or minute;
preprocessing all the historical data; the pretreatment comprises the following steps: carrying out normalization processing and classification processing on all the historical data; all the historical data meet normal distribution after being subjected to normalization processing; the classification processing comprises the following steps: performing data classification on the historical data according to the four dimensions of the time, the outdoor temperature, the application scene and the business to obtain four subclasses, subdividing the four subclasses by using a decision tree model to obtain classified data, and finally constructing a training data set by using all the classified data;
applying linear regression analysis to the classified data to fit and construct a regression model; the linear regression analysis fitting comprises: taking each time period in the time as an independent variable, and taking the energy consumption value corresponding to the time period as a dependent variable, and performing linear fitting to obtain a first fitting relational expression; taking the square of the outdoor temperature as an independent variable and the energy consumption value corresponding to the outdoor temperature as a dependent variable, and performing linear fitting to obtain a second fitting relational expression; taking the application scene as an independent variable and the energy consumption value corresponding to the application scene as a dependent variable, and performing linear fitting to obtain a third fitting relational expression; taking the service as an independent variable and the energy consumption value corresponding to the service as a dependent variable, and performing linear fitting to obtain a fourth fitting relational expression; constructing a target function according to the first fitting relation, the second fitting relation, the third fitting relation and the fourth fitting relation; the objective function is the regression model; the objective function takes the time, the outdoor temperature, the application scene and the service as independent variables, and takes the energy consumption value of the energy consumption unit as a dependent variable;
predicting a future expected energy consumption value of the energy consumption unit and a future expected total energy consumption value of the building according to the objective function;
the building energy consumption modeling method further comprises the following steps:
measuring to obtain real-time data endowed with marking information;
drawing a scatter plot comparison graph according to the real-time energy consumption value of the energy consumption unit in the real-time data and the expected energy consumption value;
when the scattered point contrast graph approaches to a straight line represented by x, determining that the objective function is a reasonable function, otherwise, determining that the objective function is unreasonable and needs to be reconstructed;
the marking information of the real-time data comprises: time, outdoor temperature, application scenario, service;
the building energy consumption modeling method further comprises the following steps:
solving an extreme value of the energy consumption unit and a total energy consumption extreme value of the building by applying a Lagrange multiplier method to the target function;
the Lagrange multiplier method specifically comprises the following steps: controlling the rest of independent variables by limiting one or more independent variables in the time, the outdoor temperature, the application scene and the business, further obtaining an energy consumption extreme value of the energy consumption unit and a total energy consumption extreme value of the building, and further determining the independent variable which has the greatest influence on energy consumption;
the normalization processing adopts a Z-score standardization method and uses a transformation function
Processing the historical data to enable the processed historical data to meet normal distribution;
wherein μ is a mean of all the historical data, σ is a standard deviation of all the historical data, and x is one of the historical dataX is described*The historical data after the x processing is carried out;
after the normalization processing and before the classification processing, vectorizing the historical data;
the vectorization processing specifically includes: and sorting the historical data and storing the sorted historical data into a matrix according to a set rule so as to carry out the classification treatment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710537577.XA CN107315884B (en) | 2017-07-04 | 2017-07-04 | Building energy consumption modeling method based on linear regression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710537577.XA CN107315884B (en) | 2017-07-04 | 2017-07-04 | Building energy consumption modeling method based on linear regression |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107315884A CN107315884A (en) | 2017-11-03 |
| CN107315884B true CN107315884B (en) | 2020-12-18 |
Family
ID=60180589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710537577.XA Active CN107315884B (en) | 2017-07-04 | 2017-07-04 | Building energy consumption modeling method based on linear regression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107315884B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108805333A (en) * | 2018-05-08 | 2018-11-13 | 中国银行股份有限公司 | The batch operation operation of core banking system takes prediction technique and device |
| CN109255472A (en) * | 2018-08-20 | 2019-01-22 | 天津科技大学 | A kind of Office Building Energy Consumption prediction technique based on Multivariate adaptive regression splines batten |
| CN109409605B (en) * | 2018-10-31 | 2021-09-24 | 山东建筑大学 | Quasi-dynamic energy consumption calculation method and optimal design method for near-zero energy consumption residence |
| CN110031877B (en) * | 2019-04-17 | 2020-05-26 | 山东科技大学 | GRNN model-based regional NWP troposphere delay correction method |
| CN110188963A (en) * | 2019-06-05 | 2019-08-30 | 中国矿业大学(北京) | Return the building energy consumption prediction technique with gradient lift scheme based on minimum angular convolution |
| CN110701732B (en) * | 2019-12-10 | 2020-06-16 | 南昌掘策数据服务有限公司 | Energy consumption data analysis method and system and energy saving method and system of central air conditioner |
| CN111563774A (en) * | 2020-05-08 | 2020-08-21 | 上海腾暨物联网科技有限公司 | Method and system for constructing coal price index prediction and supply-demand relation index |
| CN111784133B (en) * | 2020-06-22 | 2023-01-24 | 上海化学工业区中法水务发展有限公司 | Method and equipment for making sewage plant energy consumption performance index |
| CN111967756A (en) * | 2020-08-11 | 2020-11-20 | 中国科学院城市环境研究所 | Building energy consumption carbon emission determination method and system of target driving source |
| CN112258337B (en) * | 2020-09-14 | 2024-03-12 | 陕西讯格信息科技有限公司 | Self-complement correction base station energy consumption model prediction method |
| CN112150631B (en) * | 2020-09-23 | 2021-09-21 | 浙江大学 | Real-time energy consumption optimization drawing method and device based on neural network |
| CN113792490B (en) * | 2021-09-16 | 2024-07-02 | 国网江苏省电力有限公司营销服务中心 | Cement mixer energy consumption modeling method based on support vector regression machine |
| WO2024000570A1 (en) * | 2022-07-01 | 2024-01-04 | 嘉兴尚坤科技有限公司 | Building energy consumption prediction method and system based on multiple linear regression and cluster analysis |
| CN115481813B (en) * | 2022-10-09 | 2024-05-31 | 武汉理工大学 | New energy bus energy consumption prediction method based on machine learning |
| CN116680935B (en) * | 2023-07-31 | 2023-10-13 | 天津六百光年智能科技有限公司 | Two-network water supply prediction model construction method based on piecewise linear function |
| CN117371624B (en) * | 2023-12-07 | 2024-02-20 | 邢台职业技术学院 | Building energy-saving transformation optimization management method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
| CN103194553A (en) * | 2013-04-07 | 2013-07-10 | 昆明理工大学 | Oxygen usage amount control method for steel smelting blast furnace based on least square support vector machine |
| CN104732298A (en) * | 2015-04-02 | 2015-06-24 | 南京天溯自动化控制系统有限公司 | Method for achieving EMS load prediction based on decision tree and linear regression |
| CN104866725A (en) * | 2015-06-01 | 2015-08-26 | 河南中烟工业有限责任公司 | Method for predicting steam consumption of cigarette enterprise on the basis of least squares support vector machine |
| CN105096685A (en) * | 2015-08-13 | 2015-11-25 | 中国石油化工股份有限公司 | Multi-perception emergency training system for petrochemical fire scenario |
| CN105631539A (en) * | 2015-12-25 | 2016-06-01 | 上海建坤信息技术有限责任公司 | Intelligent building energy consumption prediction method based on support vector machine |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10452034B2 (en) * | 2015-12-16 | 2019-10-22 | Johnson Controls Technology Company | Central plant control system with building energy load estimation |
| US10127237B2 (en) * | 2015-12-18 | 2018-11-13 | International Business Machines Corporation | Assignment of data within file systems |
-
2017
- 2017-07-04 CN CN201710537577.XA patent/CN107315884B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103024761A (en) * | 2011-09-26 | 2013-04-03 | 艾默生网络能源有限公司 | Establishing method for energy consumption model of base station, and energy consumption predicating method and device |
| CN103194553A (en) * | 2013-04-07 | 2013-07-10 | 昆明理工大学 | Oxygen usage amount control method for steel smelting blast furnace based on least square support vector machine |
| CN104732298A (en) * | 2015-04-02 | 2015-06-24 | 南京天溯自动化控制系统有限公司 | Method for achieving EMS load prediction based on decision tree and linear regression |
| CN104866725A (en) * | 2015-06-01 | 2015-08-26 | 河南中烟工业有限责任公司 | Method for predicting steam consumption of cigarette enterprise on the basis of least squares support vector machine |
| CN105096685A (en) * | 2015-08-13 | 2015-11-25 | 中国石油化工股份有限公司 | Multi-perception emergency training system for petrochemical fire scenario |
| CN105631539A (en) * | 2015-12-25 | 2016-06-01 | 上海建坤信息技术有限责任公司 | Intelligent building energy consumption prediction method based on support vector machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107315884A (en) | 2017-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107315884B (en) | Building energy consumption modeling method based on linear regression | |
| CN106874581B (en) | Building air conditioner energy consumption prediction method based on BP neural network model | |
| CN107392368B (en) | Meteorological forecast-based office building dynamic heat load combined prediction method | |
| CN112990556A (en) | User power consumption prediction method based on Prophet-LSTM model | |
| CN115276006A (en) | Load prediction method and system for power integration system | |
| CN105117810A (en) | Residential electricity consumption mid-term load prediction method under multistep electricity price mechanism | |
| CN107944612B (en) | Bus net load prediction method based on ARIMA and phase space reconstruction SVR | |
| CN111191811A (en) | Cluster load prediction method and device and storage medium | |
| CN115099511A (en) | Photovoltaic power probability estimation method and system based on optimized copula | |
| CN112529234A (en) | Surface water quality prediction method based on deep learning | |
| CN109063892A (en) | Industry watt-hour meter prediction technique based on BP-LSSVM combination optimization model | |
| CN113393028A (en) | Load prediction method based on data mining technology | |
| CN109858700A (en) | BP neural network heating system energy consumption prediction technique based on similar screening sample | |
| CN110690701A (en) | Analysis method for influence factors of abnormal line loss | |
| Zekić-Sušac et al. | Cluster analysis and artificial neural networks in predicting energy efficiency of public buildings as a cost-saving approach | |
| CN110717581A (en) | Short-term load prediction method based on temperature fuzzy processing and DBN | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN110489893B (en) | Variable weight-based bus load prediction method and system | |
| CN117595231A (en) | Intelligent power grid distribution management system and method thereof | |
| CN112257958A (en) | Power saturation load prediction method and device | |
| CN116565850A (en) | Wind power ultra-short-term prediction method based on QR-BLSTM | |
| Gu et al. | Employment Quality Evaluation Model Based on Hybrid Intelligent Algorithm | |
| CN115759343A (en) | E-LSTM-based user electric quantity prediction method and device | |
| CN114818849A (en) | Convolution neural network based on big data information and anti-electricity-stealing method based on genetic algorithm | |
| CN107025497A (en) | A kind of electric load method for early warning and device based on Elman neutral nets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |